overseer

Adversarial review of PRs and diffs before merge. Use when finishing a PR, before merging to main, or user says 'review this diff', 'check this PR', 'is this ready to merge'. Detects slop, security issues, inconsistencies.

5 stars

bybrolag

View on GitHub Installation ↓

Best use case

overseer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using overseer should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/overseer/SKILL.md --create-dirs "https://raw.githubusercontent.com/brolag/neural-claude-code/main/skills/overseer/skill.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/overseer/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How overseer Compares

Feature / Agent	overseer	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# /overseer — Code Review

## Usage
```
/overseer              # review current branch diff
/overseer src/api/     # review specific path
/overseer --pr 123     # review specific PR
```

## Process

1. Get the diff: `git diff main...HEAD` (or specific PR/path)
2. Read CLAUDE.md for project conventions
3. Review each changed file for:

### Security
- SQL/command injection
- XSS vulnerabilities
- Exposed secrets or API keys
- Missing input validation
- Unsafe file operations

### Quality
- Functions >50 lines
- Nested conditionals >3 levels
- Duplicated logic
- Missing error handling
- Unused imports or dead code

### Consistency
- Follows project conventions (from CLAUDE.md)
- Code style matches existing files
- Tests included for new features
- Naming is consistent

## Output

```markdown
## Overseer Review: [feature/fix name]

**Score**: X/10

| Severity | Issue | Location | Fix |
|----------|-------|----------|-----|
| High | ... | file:line | ... |

**Verdict**: APPROVE (>=8) or FIX REQUIRED (<8)
```

## Rules
- Score 8-10: approve
- Score 5-7: fix required, provide specific suggestions
- Score 1-4: block merge, detailed issues listed
- Never approve hardcoded secrets
- Never approve code without tests for new features

Related Skills

slop-scan

from brolag/neural-claude-code

Scan a codebase for accumulated slop, technical debt, dead code, and refactor opportunities. Use when user says 'scan for slop', 'find tech debt', 'what needs cleanup', or before a refactor sprint.

forge

from brolag/neural-claude-code

Full dev pipeline: scan, plan, execute, review, ship. Use when user says /forge or wants the full quality pipeline on a task. Don't use for quick fixes (<25 LOC) or docs-only changes.

overseerr

from Demerzels-lab/elsamultiskillagent

Request movies/TV and monitor request status via the Overseerr API (stable Overseerr, not the beta Seerr rewrite).

subagent-overseer

from Demerzels-lab/elsamultiskillagent

Monitor sub-agent health and progress via a pull-based bash daemon.

artifact-overseer

from kody-w/rappterbook

Oversee whatever artifact seed is currently active — verify agents are producing real code, not coasting on fluff. Reads the active seed from seeds.json and adapts to any project or deliverable.

swe-cli-skills

from SylphAI-Inc/skills

Senior engineer CLI expertise for AI agents — workflows, safety guardrails, gotchas, and anti-patterns across cloud, IaC, containers, databases, dev tools, and platforms

DevOps & Infrastructure

PicoClaw Fleet

from EricGrill/agents-skills-plugins

Orchestrate a fleet of remote PicoClaw workers over SSH for fast, ephemeral one-shot tasks.

DevOps & Infrastructure

VibeCollab — Setup Instructions for AI Assistants

from flashpoint493/VibeCollab

You are helping a user set up VibeCollab in their project.

Workflow & Productivity

raycast-extension-docs

from lemikeone/Codex-skill-raycast-extension

Guidance for building, debugging, and publishing Raycast extensions using the Raycast documentation set. Use when Codex needs to create or modify Raycast extensions (React/TypeScript/Node), consult Raycast API reference or UI components, build AI extensions, handle manifest/lifecycle/preferences, troubleshoot issues, or prepare/publish extensions to the Raycast Store or Teams.

Coding & Development

evomap

from hyz0906/paper

Connect to the EvoMap collaborative evolution marketplace. Publish Gene+Capsule bundles, fetch promoted assets, claim bounty tasks, register as a worker, create and express recipes, collaborate in sessions, bid on bounties, resolve disputes, and earn credits via the GEP-A2A protocol. Use when the user mentions EvoMap, evolution assets, A2A protocol, capsule publishing, agent marketplace, worker pool, recipe, organism, session collaboration, or service marketplace.

AI Agent Marketplace

maestro

from Viniciuscarvalho/maestro

Intelligent skill knowledge gateway. Routes tasks to the right knowledge without loading all skills into context. MUST be consulted before any coding task — call the search_skills MCP tool to retrieve relevant expertise from 100+ indexed skills covering Swift, SwiftUI, concurrency, testing, architecture, performance, and security.

Coding & Development

opentui

from LeonardoTrapani/better-skills

Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler. Use for any TUI development task including components, layout, keyboard handling, animations, and testing.

Coding & Development